Estimating population density using open-access satellite images and geographic information system: Case of Al Ain city, UAE

Abstract

Efficient and real-time estimates of population density are crucial for monitoring urban systems and disaster response. To develop this capability, this study estimates population density using covariates derived from remote-sensing images [e.g., building density, vegetation temperature light population index (VTLPI), and day–night band (DNB)]. Data were obtained from open-access satellite images, specifically Sentinel 2A, Landsat 8, and NPP-VIIRS images. Building density, VTLPI, and DNB were extracted at the district level and compared with population density. Furthermore, vector data from geographic information systems, such as human points of interest and road networks, were used to develop a geographically weighted regression model for estimating population density. Building density and DNB correlated positively with population density (r = 0.89), and population density correlated positively with the VTLPI (r = 0.75). Although all covariates correlated positively with estimates of population density, building density and the DNB showed the best correlation. Furthermore, both parameters were considerably related to human points of interest and road network density. Finally, using geographically weighted regression (GWR) and multiple linear regression (MLR) with the building density, DNB, and human points of interest as input, we predicted the population density. The GWR model built from independent variables correlates well with the population density (AICc = 526; R2 adj. = 0.89). Overall, the GWR and MLR produce similar results. To assess the transferability of the GWR model used for Al Ain, it was tested on Abu Dhabi, and the results produce an accuracy of 36%. This low accuracy may be attributed to the acquisition dates of the census data being different from those of the human points of interest. Further research is required to address such limitations in the proposed method and to provide additional support for using open-access remote-sensing images to estimate population density.